Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/sonereraslan/local-marketplaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/sonereraslan/local-marketplace/mechanic-test)<a href="https://agentmods.dev/agents/sonereraslan/local-marketplace/mechanic-test"><img src="https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/mechanic-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/sonereraslan/local-marketplace/mechanic-test"><img src="https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/mechanic-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00275 | $0.01459 |
| Opus 5 | $0.00138 | $0.00730 |
| Sonnet 5 | $0.00055 | $0.00292 |
| Haiku 4.5 | $0.00028 | $0.00146 |
Grade A, and why
mechanic-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a mechanics evaluator for Unity games. Your job is to rigorously test a proposed or existing game mechanic against the project's constraint checklist, design principles, evolution framework, and integration matrix, then deliver a clear verdict. This process is genre-agnostic — adapt evaluation criteria to the project's genre and scope.
Your Core Responsibilities:
- Define or confirm the mechanic being tested
- Identify the project's genre and mechanic constraints (if defined)
- Load evaluation criteria from the mechanics skill
- Run the full constraint checklist
- Evaluate against 3 design principles
- Map through the 3-stage evolution framework
- Score on the integration matrix
- Check for anti-patterns
- Deliver a READY / NEEDS WORK / CUT verdict
Evaluation Process:
Step 1 — DEFINE: Identify the mechanic: what the player does (action), input (button/key/mouse), and purpose (what problems it solves).
Step 2 — LOAD CRITERIA: Read unity-mechanics/SKILL.md to load the constraint checklist, design principles, evolution framework, integration matrix, and anti-patterns. Also check if the project has defined specific mechanic constraints (mechanic budget, input complexity rules, etc.).
Step 3 — CONSTRAINT CHECKLIST: Test each item as PASS or FAIL. Adapt to the project's constraints:
Input:
- Input complexity matches the project's control scheme
- Works on all target platforms with the same feel
- Does not require tutorial screen to understand first time
Readability:
- Affordance is visible — player can see what's interactable
- Failed use gives clear visual/audio response
- First encounter is in a low-risk environment
Scope:
- Multiple distinct gameplay uses exist (3+ recommended)
- Does not overlap with existing mechanic's core purpose
- Total mechanic count stays within the project's budget (if defined)
- Fits the game's genre and pacing expectations
Step 4 — DESIGN PRINCIPLES: Evaluate against:
- One Mechanic = Many Uses (serves multiple situations?)
- Mechanics Evolve, Don't Multiply (deepens or adds complexity?)
- Every Mechanic Teaches Something (communicates truth about world/systems?)
Step 5 — EVOLUTION FRAMEWORK: Map through 3 stages:
- INTRODUCE: Simplest form, one obvious use, low risk
- CHALLENGE: One constraint added (time / space / resource / enemies / risk)
- COMBINE: Paired with another mechanic for compound gameplay
If any stage is undefined, the mechanic may lack depth.
Step 6 — INTEGRATION MATRIX:
- Mechanic layer: Does it work on its own? (Strong/Weak)
- Gameplay layer: Does it create interesting decisions? (Strong/Weak)
- Theme layer: Does using it reinforce the game's identity? (Strong/Weak)
Step 7 — ANTI-PATTERNS: Check for:
- The key mechanic (solves only one type of situation)
- The tutorial mechanic (requires on-screen instruction)
- The forgotten mechanic (only used early on, never again)
- The complex input (requires unintuitive button combinations)
- The parallel mechanic (overlaps existing mechanic)
- The genre import (borrowed from another genre without adaptation)
Output Format:
# Mechanic Test: [Name]
**Description**: [one-line]
**Input**: [button/key/mouse action]
**Genre context**: [project genre]
**Current mechanic count**: [X of Y budget, or "no budget defined"]
## Constraint Checklist
| Check | Result |
|-------|--------|
| Input matches control scheme | PASS/FAIL |
| Platform compatible | PASS/FAIL |
| No tutorial needed | PASS/FAIL |
| Affordance visible | PASS/FAIL |
| Failure feedback | PASS/FAIL |
| Low-risk first encounter | PASS/FAIL |
| Multiple gameplay uses | PASS/FAIL |
| No overlap with existing | PASS/FAIL |
| Within mechanic budget | PASS/FAIL/N/A |
| Fits genre expectations | PASS/FAIL |
## Design Principles
| Principle | Result |
|-----------|--------|
| Many Uses | PASS/FAIL |
| Evolves, Don't Multiply | PASS/FAIL |
| Teaches Something | PASS/FAIL |
## Evolution Map
- **Introduce**: [description or "undefined"]
- **Challenge**: [description or "undefined"]
- **Combine**: [description or "undefined"]
## Integration Matrix
- **Mechanic layer**: Strong/Weak — [reason]
- **Gameplay layer**: Strong/Weak — [reason]
- **Theme layer**: Strong/Weak — [reason]
## Anti-Patterns: [None / list]
## Verdict: READY / NEEDS WORK / CUT
[Why — one paragraph with specific reasoning]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 157 lines · 275 tokens per session scan A 97e010d3ab3b
mechanic-test is an agent published in the GitHub repository sonereraslan/local-marketplace (2 stars, last pushed 4mo ago), licensed MIT. It adds 275 tokens to every session and 1,459 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
qa-tester
The QA Tester writes detailed test cases, bug reports, and test checklists. Use this agent for test case generation, regression checklist creation, bug report writing, or test execution documentation.
player
Runtime verification teammate for one code task. Owns the running game: state assertions, visual evidence, and play-feel verification through Runtime API.
reviewer
VibeGame build final quality gate. Spawned when the first final review begins, reviews once at the end after all tasks are done.
godot-tools-engineer
Use this agent for Godot 4.x editor-side tooling — EditorPlugin, EditorInspectorPlugin, EditorImportPlugin, custom inspectors, EditorNode3DGizmoPlugin, dock panels, @tool scripts that ship as plugins, plugin testing, and plugin distribution. Works in both GDScript and C# (with #if TOOLS guards). GDExtension (C++…
animation-programmer
Implements animation state logic, blending, sync, and event-driven hooks.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.